NanoGPT
TEE-only GatewayPay-per-prompt confidential inference — TEE-backed models with ECDSA per-request attestation
NanoGPT runs a curated set of open-source models inside Trusted Execution Environments (TEE), providing hardware-enforced confidentiality for prompts and responses. TEE models are identified by a TEE/ prefix and can be cryptographically verified: a dedicated attestation endpoint returns the hardware quote, and a per-request ECDSA signature endpoint lets clients confirm their specific completion was produced inside the enclave. No account or subscription required — anonymous cryptocurrency payments accepted.
API Features
OpenAI Compatible ✓
Streaming ✓
Function Calling —
Batch Inference —
Vision —
Embeddings —
Attestation Status
View full details →Last checked: Jun 18, 2026, 11:05 AM
Hardware verified, provenance incomplete TEE evidence passed, but source or image provenance is not fully pinned for every check.
6 verified 20 partial 0 failed 5 unavailable
Hardware 26/31 good Freshness 12/31 good Key binding 12/31 good Workload 16 bad Provenance 20 warning Availability 5 warning
Source provenance incomplete 14 Image provenance incomplete 6 Endpoint unavailable 5
DeepSeek V3.2 (TEE) Intel TDX TEE-only Gateway Details DeepSeek V4 Pro (TEE) Intel TDX TEE-only Gateway Details Gemma 4 31B (TEE) AMD SEV-SNP TEE-only Gateway Details GLM 5.1 (TEE) Intel TDX TEE-only Gateway Details GPT-OSS 120B (TEE) Intel TDX TEE-only Gateway Details Kimi K2.6 (TEE) Intel TDX TEE-only Gateway Details Llama 3.3 70B (TEE) AMD SEV-SNP TEE-only Gateway Details Qwen3.5 397B (TEE) Intel TDX TEE-only Gateway Details TEE/deepseek V3.1 (TEE) Intel TDX TEE-only Gateway Details TEE/deepseek V4 Flash (TEE) Intel TDX TEE-only Gateway Details TEE/deepseek V4 Pro:thinking (TEE) Intel TDX TEE-only Gateway Details TEE/gemma 3 27b It (TEE) Details TEE/gemma 4 26b A4b Uncensored (TEE) Intel TDX TEE-only Gateway Details TEE/gemma 4 31b It (TEE) Details TEE/gemma4 31b:thinking (TEE) AMD SEV-SNP TEE-only Gateway Details TEE/glm 4.7 (TEE) Intel TDX TEE-only Gateway Details TEE/glm 4.7 Flash (TEE) Intel TDX TEE-only Gateway Details TEE/glm 5 (TEE) Intel TDX TEE-only Gateway Details TEE/glm 5.1 Thinking (TEE) Intel TDX TEE-only Gateway Details TEE/glm 5.2 (TEE) Details TEE/gpt Oss 20b (TEE) Intel TDX TEE-only Gateway Details TEE/kimi K2.5 (TEE) Details TEE/kimi K2.5 Thinking (TEE) Details TEE/minimax M2.5 (TEE) Intel TDX TEE-only Gateway Details TEE/qwen2.5 Vl 72b Instruct (TEE) Intel TDX TEE-only Gateway Details TEE/qwen3 30b A3b Instruct 2507 (TEE) Intel TDX TEE-only Gateway Details TEE/qwen3.5 122b A10b (TEE) Intel TDX TEE-only Gateway Details TEE/qwen3.5 27b (TEE) Intel TDX TEE-only Gateway Details TEE/qwen3.6 27b (TEE) Intel TDX TEE-only Gateway Details TEE/qwen3.6 35b A3b (TEE) Intel TDX TEE-only Gateway Details TEE/qwen3.6 35b A3b Uncensored (TEE) Intel TDX TEE-only Gateway Details
Models & Pricing
| Model | Family | Context | Max Out | Input /M | Output /M | Free |
|---|---|---|---|---|---|---|
| Qwen3.6 27B | Qwen | 256K | — | $0.32 | $2.70 | — |
| Qwen3 235B A22B | Qwen | 250K | — | $0.13 | $0.50 | — |
| GPT-OSS 120B | OpenAI GPT | 128K | — | $2.00 | $2.00 | — |
| GPT-OSS 20B | OpenAI GPT | 128K | — | $0.20 | $0.80 | — |
| Qwen2.5-VL 72B | Qwen | 64K | — | $0.70 | $0.70 | — |
| DeepSeek V3.1 | DeepSeek | 160K | — | $1.00 | $2.50 | — |
| DeepSeek V3.2 | DeepSeek | 160K | — | $0.50 | $1.00 | — |
| Qwen3 30B A3B | Qwen | 256K | — | $0.15 | $0.45 | — |
| Qwen3.6 35B A3B Uncensored | Qwen | 128K | — | $0.30 | $1.50 | — |
| Qwen3.5 27B | Qwen | 256K | — | $0.30 | $2.40 | — |
| Qwen3.5 397B A17B | Qwen | 256K | — | $0.55 | $3.50 | — |
| Qwen3.5 122B A10B | Qwen | 256K | — | $0.46 | $3.68 | — |
| Gemma 4 31B IT | Google Gemma | 256K | — | $0.15 | $0.46 | — |
| Gemma 4 26B A4B Uncensored | Google Gemma | 64K | — | $0.15 | $0.70 | — |
| GLM 4.7 Flash | ZhipuAI GLM | 198K | — | $0.15 | $0.50 | — |
| Gemma 3 27B | Google Gemma | 128K | — | $0.20 | $0.80 | — |
| Gemma 4 31B | Google Gemma | 256K | — | $0.45 | $1.00 | — |
| Gemma 4 31B Thinking | Google Gemma | 256K | — | $0.45 | $1.00 | — |
| Llama 3.3 70B | Meta Llama | 125K | — | $2.00 | $2.00 | — |
| DeepSeek V4 Pro | DeepSeek | 781K | — | $1.50 | $5.25 | — |
| DeepSeek V4 Pro Thinking | DeepSeek | 781K | — | $1.50 | $5.25 | — |
| MiniMax M2.5 | MiniMax | 192K | — | $0.20 | $1.38 | — |
| Kimi K2.5 | Moonshot AI | 125K | — | $0.60 | $3.00 | — |
| Kimi K2.5 Thinking | Moonshot AI | 125K | — | $0.60 | $3.00 | — |
| Kimi K2.6 | Moonshot AI | 4K | — | $1.50 | $5.25 | — |
| GLM 4.7 | ZhipuAI GLM | 128K | — | $0.85 | $3.30 | — |
| GLM 5 | ZhipuAI GLM | 198K | — | $1.20 | $3.50 | — |
| GLM 5.1 | ZhipuAI GLM | 4K | — | $1.50 | $5.25 | — |
| GLM 5.1 Thinking | ZhipuAI GLM | 4K | — | $1.50 | $5.25 | — |